Parallel importance sampling in conditional linear Gaussian networks

Antonio Salmerón; Darío  Ramos-López; Hanen Borchani; Ana Maria Martinez; Andres R. Masegosa; Antonio Fernández; Helge Langseth; Anders Læsø Madsen; Thomas Dyhre Nielsen

doi:10.1007/978-3-319-24598-0_4

Parallel importance sampling in conditional linear Gaussian networks

Antonio Salmerón, Darío Ramos-López, Hanen Borchani, Ana Maria Martinez, Andres R. Masegosa, Antonio Fernández, Helge Langseth, Anders Læsø Madsen, Thomas Dyhre Nielsen

Institut for Datalogi

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

7 Citationer (Scopus)

486 Downloads (Pure)

Abstract

In this paper we analyse the problem of probabilistic inference in CLG networks when evidence comes in streams. In such situations, fast and scalable algorithms, able to provide accurate responses in a short time are required. We consider the instantiation of variational inference and importance sampling, two well known tools for probabilistic inference, to the CLG case. The experimental results over synthetic networks show how a parallel version importance sampling, and more precisely evidence weighting, is a promising scheme, as it is accurate and scales up with respect to available computing resources.

Originalsprog	Engelsk
Titel	Advances in Artificial Intelligence : 16th Conference of the Spanish Association for Artiﬁcial Intelligence, CAEPIA 2015 Albacete, Spain, November 9–12, 2015 Proceedings
Redaktører	José M. Puerta, José A. Gámez, Bernabe Dorronsoro, Edurne Barrenechea, Alicia Troncoso, Bruno Baruque, Mikel Galar
Forlag	Springer
Publikationsdato	2015
Sider	36-46
ISBN (Trykt)	978-3-319-24597-3
ISBN (Elektronisk)	978-3-319-24598-0
DOI	https://doi.org/10.1007/978-3-319-24598-0_4
Status	Udgivet - 2015
Begivenhed	Conference of the Spanish Association for Artiﬁcial Intelligence, CAEPIA 2015 - Albacete, Spanien Varighed: 9 nov. 2015 → 12 nov. 2015 Konferencens nummer: 16th

Konference

Konference	Conference of the Spanish Association for Artiﬁcial Intelligence, CAEPIA 2015
Nummer	16th
Land/Område	Spanien
By	Albacete
Periode	09/11/2015 → 12/11/2015

Navn	Lecture Notes in Computer Science
Nummer	9422
ISSN	0302-9743

Adgang til dokumentet

10.1007/978-3-319-24598-0_4

salmeron_amidst_caepiaIndsendt manuskript, 410 KB

AUB Link

Søg efter materialet i Aalborg Universitetsbiblioteks søgemaskine

AMIDST: Analysis of MassIve Data STreams - AMIDST
Madsen, A. L., Rommerdahl Bock, A., Nielsen, T. D. & Martinez, A. M.
European Union’s Seventh Framework Programme for research, technological development and demonstration
01/01/2014 → 31/12/2016
Projekter: Projekt › Forskning

Citationsformater

Salmerón, A., Ramos-López, D., Borchani, H., Martinez, A. M., Masegosa, A. R., Fernández, A., Langseth, H., Madsen, A. L., & Nielsen, T. D. (2015). Parallel importance sampling in conditional linear Gaussian networks. I J. M. Puerta, J. A. Gámez, B. Dorronsoro, E. Barrenechea, A. Troncoso, B. Baruque, & M. Galar (red.), Advances in Artificial Intelligence: 16th Conference of the Spanish Association for Artiﬁcial Intelligence, CAEPIA 2015 Albacete, Spain, November 9–12, 2015 Proceedings (s. 36-46). Springer. https://doi.org/10.1007/978-3-319-24598-0_4

Salmerón, Antonio ; Ramos-López, Darío ; Borchani, Hanen et al. / Parallel importance sampling in conditional linear Gaussian networks. Advances in Artificial Intelligence: 16th Conference of the Spanish Association for Artiﬁcial Intelligence, CAEPIA 2015 Albacete, Spain, November 9–12, 2015 Proceedings. red. / José M. Puerta ; José A. Gámez ; Bernabe Dorronsoro ; Edurne Barrenechea ; Alicia Troncoso ; Bruno Baruque ; Mikel Galar. Springer, 2015. s. 36-46 (Lecture Notes in Computer Science; Nr. 9422).

@inproceedings{8438e1470d26401590b173dd32942fb4,

title = "Parallel importance sampling in conditional linear Gaussian networks",

abstract = "In this paper we analyse the problem of probabilistic inference in CLG networks when evidence comes in streams. In such situations, fast and scalable algorithms, able to provide accurate responses in a short time are required. We consider the instantiation of variational inference and importance sampling, two well known tools for probabilistic inference, to the CLG case. The experimental results over synthetic networks show how a parallel version importance sampling, and more precisely evidence weighting, is a promising scheme, as it is accurate and scales up with respect to available computing resources.",

author = "Antonio Salmer{\'o}n and Dar{\'i}o Ramos-L{\'o}pez and Hanen Borchani and Martinez, {Ana Maria} and Masegosa, {Andres R.} and Antonio Fern{\'a}ndez and Helge Langseth and Madsen, {Anders L{\ae}s{\o}} and Nielsen, {Thomas Dyhre}",

year = "2015",

doi = "10.1007/978-3-319-24598-0_4",

language = "English",

isbn = "978-3-319-24597-3",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

number = "9422",

pages = "36--46",

editor = "Puerta, {Jos{\'e} M.} and G{\'a}mez, {Jos{\'e} A.} and Bernabe Dorronsoro and Edurne Barrenechea and Alicia Troncoso and Bruno Baruque and Mikel Galar",

booktitle = "Advances in Artificial Intelligence",

address = "Germany",

note = "Conference of the Spanish Association for Artiﬁcial Intelligence, CAEPIA 2015 ; Conference date: 09-11-2015 Through 12-11-2015",

}

Salmerón, A, Ramos-López, D, Borchani, H, Martinez, AM, Masegosa, AR, Fernández, A, Langseth, H, Madsen, AL & Nielsen, TD 2015, Parallel importance sampling in conditional linear Gaussian networks. i JM Puerta, JA Gámez, B Dorronsoro, E Barrenechea, A Troncoso, B Baruque & M Galar (red), Advances in Artificial Intelligence: 16th Conference of the Spanish Association for Artiﬁcial Intelligence, CAEPIA 2015 Albacete, Spain, November 9–12, 2015 Proceedings. Springer, Lecture Notes in Computer Science, nr. 9422, s. 36-46, Conference of the Spanish Association for Artiﬁcial Intelligence, CAEPIA 2015 , Albacete, Spanien, 09/11/2015. https://doi.org/10.1007/978-3-319-24598-0_4

Parallel importance sampling in conditional linear Gaussian networks. / Salmerón, Antonio; Ramos-López, Darío ; Borchani, Hanen et al.
Advances in Artificial Intelligence: 16th Conference of the Spanish Association for Artiﬁcial Intelligence, CAEPIA 2015 Albacete, Spain, November 9–12, 2015 Proceedings. red. / José M. Puerta; José A. Gámez; Bernabe Dorronsoro; Edurne Barrenechea; Alicia Troncoso; Bruno Baruque; Mikel Galar. Springer, 2015. s. 36-46 (Lecture Notes in Computer Science; Nr. 9422).

Publikation: Bidrag til bog/antologi/rapport/konference proceeding › Konferenceartikel i proceeding › Forskning › peer review

TY - GEN

T1 - Parallel importance sampling in conditional linear Gaussian networks

AU - Salmerón, Antonio

AU - Ramos-López, Darío

AU - Borchani, Hanen

AU - Martinez, Ana Maria

AU - Masegosa, Andres R.

AU - Fernández, Antonio

AU - Langseth, Helge

AU - Madsen, Anders Læsø

AU - Nielsen, Thomas Dyhre

N1 - Conference code: 16th

PY - 2015

Y1 - 2015

N2 - In this paper we analyse the problem of probabilistic inference in CLG networks when evidence comes in streams. In such situations, fast and scalable algorithms, able to provide accurate responses in a short time are required. We consider the instantiation of variational inference and importance sampling, two well known tools for probabilistic inference, to the CLG case. The experimental results over synthetic networks show how a parallel version importance sampling, and more precisely evidence weighting, is a promising scheme, as it is accurate and scales up with respect to available computing resources.

AB - In this paper we analyse the problem of probabilistic inference in CLG networks when evidence comes in streams. In such situations, fast and scalable algorithms, able to provide accurate responses in a short time are required. We consider the instantiation of variational inference and importance sampling, two well known tools for probabilistic inference, to the CLG case. The experimental results over synthetic networks show how a parallel version importance sampling, and more precisely evidence weighting, is a promising scheme, as it is accurate and scales up with respect to available computing resources.

U2 - 10.1007/978-3-319-24598-0_4

DO - 10.1007/978-3-319-24598-0_4

M3 - Article in proceeding

SN - 978-3-319-24597-3

T3 - Lecture Notes in Computer Science

SP - 36

EP - 46

BT - Advances in Artificial Intelligence

A2 - Puerta, José M.

A2 - Gámez, José A.

A2 - Dorronsoro, Bernabe

A2 - Barrenechea, Edurne

A2 - Troncoso, Alicia

A2 - Baruque, Bruno

A2 - Galar, Mikel

PB - Springer

T2 - Conference of the Spanish Association for Artiﬁcial Intelligence, CAEPIA 2015

Y2 - 9 November 2015 through 12 November 2015

ER -

Salmerón A, Ramos-López D, Borchani H, Martinez AM, Masegosa AR, Fernández A et al. Parallel importance sampling in conditional linear Gaussian networks. I Puerta JM, Gámez JA, Dorronsoro B, Barrenechea E, Troncoso A, Baruque B, Galar M, red., Advances in Artificial Intelligence: 16th Conference of the Spanish Association for Artiﬁcial Intelligence, CAEPIA 2015 Albacete, Spain, November 9–12, 2015 Proceedings. Springer. 2015. s. 36-46. (Lecture Notes in Computer Science; Nr. 9422). doi: 10.1007/978-3-319-24598-0_4

Parallel importance sampling in conditional linear Gaussian networks

Abstract

Konference

Adgang til dokumentet

AUB Link

Fingeraftryk

Projekter

AMIDST: Analysis of MassIve Data STreams - AMIDST

Citationsformater